Job adaptability online training platform and training effect improvement method

Abstract

The application provides a post adaptability online training platform and a training effect improving method, and relates to the technical field of computers.The application comprises a content generation module, which is used for generating and storing post training courses according to a post directory to be trained; a learning map generation module, which is used for obtaining a post ability model of a target post, calling a target training course associated with the post ability model from the post training courses, and dynamically generating a personalized learning map for each target post trainee according to the target training course and a preset learning path rule; and a course matching module, which is used for outputting a personalized learning map associated with a post of an employee based on an authorized employee access interface and in response to received employee identity information; thus, the period for the employee to adapt to a new environment can be shortened, the operation and maintenance skills of all employees can be systematically improved, and the risk of misoperation can be reduced.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to an online training platform for job adaptability and a method for improving training effectiveness. Background Technology

[0002] The design and construction of a new cigarette factory, based on considerations of product quality, energy efficiency, and environmental protection, inevitably involves the introduction of new production equipment and processes. Consequently, the skills of employees on the old factory's production lines may not be adequate for the new equipment and processes, necessitating on-the-job training. This is typically achieved by sending instructors from the equipment manufacturers to provide on-site guidance, or by sending employees to the equipment manufacturers for targeted training.

[0003] Currently, traditional offline training basically uses full-course tutorials for training, which has a long training cycle, high cost, and monotonous format, resulting in slow employee adaptation to the new environment and high risk of misoperation, which urgently needs to be addressed. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide an online training platform for job adaptability and a method to improve training effectiveness, which can improve the shortcomings of traditional job training methods and solve the problems of slow employee adaptation to new environments and high risk of misoperation.

[0005] To achieve the above technical objectives, the technical solution adopted in this application is as follows:

[0006] Firstly, this application provides an online training platform for job adaptability, including:

[0007] The content generation module is used to generate and store job training tutorials based on the job list to be trained. The job list is formulated by experts in the expert database based on the key equipment and new processes introduced in the new plant. The job training tutorials include video tutorials, text tutorials, interactive quizzes, and simulated operations.

[0008] The learning map generation module is used to obtain the job competency model of the target position, retrieve the target training tutorial associated with the job competency model from the job training tutorial, and dynamically generate a personalized learning map for each trainee of the target position according to the target training tutorial and the preset learning path rules.

[0009] The tutorial matching module is used to output a personalized learning map associated with the employee's job position in response to the received employee identity information, based on the authorized employee access interface.

[0010] The assessment and scoring module is used to embed online quiz units in the learning nodes of the personalized learning map, obtain the trainees' quiz results, and calculate and accumulate the trainees' learning points according to the preset scoring rules.

[0011] The qualification linkage module is used to compare the learning points with a preset job qualification certification threshold. When the learning points reach or exceed the job qualification certification threshold, a job qualification certification trigger signal is output.

[0012] Further specifying, the learning map generation module includes: a job tagging unit, used to establish a multi-dimensional tagging system for each target job, including equipment type, process flow, and operation difficulty level, in order to construct a job competency model for the target job;

[0013] The tutorial semantic association unit is used to perform semantic analysis on the job training tutorial, generate tutorial tags, and add the tutorial tags to the multi-dimensional tag system.

[0014] The path planning engine is used to preset learning path rules and generate personalized learning maps based on the multi-dimensional tag system, tutorial tags, and preset learning path rules.

[0015] Further specifying, the assessment scoring module includes:

[0016] The learning assessment submodule is used to extract online quiz units from a preset knowledge base and embed the online quiz units into the learning nodes of the personalized learning map.

[0017] The points submodule is used to obtain the trainee's answer results and calculate and accumulate the trainee's learning points according to the preset points rules.

[0018] Furthermore, the assessment and scoring module also includes a sub-module for reinforcing incorrect answers.

[0019] The error correction reinforcement submodule is used to retrieve and re-push reinforcement tutorials and test questions associated with the error from the content generation module when a trainee makes n consecutive errors in the online question-answering unit, so that the trainee can learn and test; where n is greater than 2.

[0020] Furthermore, after outputting the job qualification authentication trigger signal, the qualification linkage module is also used for:

[0021] Electronic qualification badges are issued to trainees and their job access status is updated through the employee access interface.

[0022] Furthermore, the employee access interface is either the organizational structure interface of an enterprise office automation system or the application development interface of an instant messaging platform.

[0023] Furthermore, the preset learning path rules include mandatory sequence rules and selective recommendation rules;

[0024] The mandatory sequence rule requires that the content of the next learning node can only be unlocked after the online answer result of the previous learning node meets the passing condition;

[0025] The selective recommendation rule recommends supplementary learning content based on the trainee's job category and historical learning efficiency.

[0026] Secondly, a method for improving training effectiveness includes the following steps: generating and storing job training tutorials based on a list of jobs to be trained; the list of jobs to be trained is created by experts in an expert database based on key equipment and new processes introduced in the new plant.

[0027] Obtain the job competency model of the target position, retrieve the target training tutorial associated with the job competency model from the job training tutorial, and dynamically generate a personalized learning map for each trainee of the target position according to the target training tutorial and the preset learning path rules.

[0028] Based on the authorized employee access interface, in response to the received employee identity information, a personalized learning map associated with the employee's position is output.

[0029] An online quiz unit is embedded in the learning node of the personalized learning map to obtain the trainee's quiz results and calculate and accumulate the trainee's learning points according to the preset scoring rules.

[0030] The learning points are compared with a preset job qualification certification threshold. When the learning points reach or exceed the job qualification certification threshold, a job qualification certification trigger signal is output.

[0031] Further specifying, the step of dynamically generating personalized learning maps includes:

[0032] Establish a multi-dimensional tagging system for each target position, including equipment type, process flow, and level of operational difficulty, in order to construct a job competency model for the target position;

[0033] Semantic analysis is performed on the job training tutorials to generate tutorial tags; these tutorial tags are then added to a multi-dimensional tag system.

[0034] The system presets learning path rules and generates personalized learning maps based on the multi-dimensional tag system, tutorial tags, and preset learning path rules.

[0035] The invention employing the above technical solution has the following advantages:

[0036] In the technical solution provided in this application, the use of an online training platform for job adaptability replaces the traditional offline on-site guidance and remote learning methods. Employees can learn online anytime and anywhere without spending a lot of time traveling to and from training locations, thus significantly shortening the training cycle. At the same time, there is no need for equipment manufacturers to send instructors to the factory or send employees to learn in other locations, reducing related expenses such as transportation, accommodation, and training venues, lowering training costs, and solving the problems of long training cycles and high costs associated with traditional offline training.

[0037] By using the learning map generation module, personalized learning maps are dynamically generated based on job competency models and employees' individual basic abilities, and targeted training tutorials are pushed to avoid a "one-size-fits-all" uniform training model. At the same time, through the error correction reinforcement sub-module, reinforcement tutorials and test questions are pushed to employees' weak learning areas to help them accurately make up for their deficiencies, improve learning effectiveness, enable employees to quickly master the relevant knowledge and operating skills of new equipment and processes, shorten job adaptation time, and solve the problem of slow adaptation to new environments.

[0038] The assessment and points module allows for real-time evaluation of employee learning outcomes. The qualification linkage module links learning points to job qualification certification. Only employees whose points reach a preset threshold can obtain job qualification certification, ensuring that employees possess the necessary skills before starting work. This effectively reduces the risk of employee misoperation, guarantees the safety and stability of production in the new factory, and solves the problems of disconnect between traditional training effectiveness and job qualification, as well as the high risk of misoperation. Attached Figure Description

[0039] This application can be further illustrated by the non-limiting embodiments given in the accompanying drawings. It should be understood that the following drawings only illustrate some embodiments of this application and should not be considered as limiting the scope. For those skilled in the art, other related drawings can be obtained from these drawings without any inventive effort.

[0040] Figure 1 A schematic diagram of the structural framework of an online training platform for job adaptability provided in this application embodiment;

[0041] Figure 2 This is a schematic diagram of the structural framework of the learning map generation module in the embodiments of this application;

[0042] Figure 3 This is a schematic diagram of the structural framework of the assessment and scoring module in the embodiments of this application;

[0043] Figure 4 This is a flowchart illustrating a method for improving training effectiveness provided in an embodiment of this application. Detailed Implementation

[0044] The present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that similar or identical parts are referred to by the same reference numerals in the drawings or description. Implementations not shown or described in the drawings are forms known to those skilled in the art. In the description of this application, terms such as "first" and "second" are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0045] Reference Figure 1 This invention provides an online training platform for job adaptability, comprising:

[0046] The content generation module 110 is used to generate and store job training tutorials based on the job list to be trained; the job list to be trained is formulated by experts in the expert database based on the key equipment and new processes introduced in the new plant; the job training tutorials include video tutorials, graphic tutorials, interactive quizzes and simulated operations, etc.

[0047] The learning map generation module 120 is used to obtain the job competency model of the target position, retrieve the target training tutorial associated with the job competency model from the job training tutorial, and dynamically generate a personalized learning map for each trainee of the target position according to the target training tutorial and the preset learning path rules.

[0048] The tutorial matching module 130 is used to output a personalized learning map associated with the employee's position based on the authorized employee access interface and in response to the received employee identity information; the employee access interface is the organizational structure interface of the enterprise office automation system or the application development interface of the instant messaging platform.

[0049] The assessment and scoring module 140 is used to embed online quiz units in the learning nodes of the personalized learning map, obtain the quiz results of trainees, and calculate and accumulate the learning points of trainees according to preset scoring rules.

[0050] The qualification linkage module 150 is used to compare the learning points with a preset job qualification certification threshold, and output a job qualification certification trigger signal when the learning points reach or exceed the job qualification certification threshold.

[0051] The training job catalog and expert database in this embodiment can be determined during the construction of the new cigarette factory. The expert database includes three core types of personnel: technical experts from equipment manufacturers, senior management personnel from the cigarette factory, and industry technical R&D experts. Among them, technical experts from equipment manufacturers must have more than 5 years of relevant equipment operation and guidance experience, and senior management personnel from the cigarette factory must have more than 3 years of experience in new factory job planning. The expert database maintenance mechanism adopts "quarterly review + dynamic update". Every quarter, the technical department of the cigarette factory organizes a review to eliminate unqualified experts (such as those who did not participate in the formulation of the job catalog or whose professional capabilities do not meet the standards) and add qualified experts to ensure the professionalism and timeliness of the expert database.

[0052] In this embodiment, the online training platform for job adaptability offers advantages over traditional training methods. The platform allows employees to learn anytime, anywhere, eliminating the need for significant time spent traveling to training locations and greatly shortening the training cycle. It also eliminates the need for equipment manufacturers to send instructors to the factory or for employees to travel to other locations for training, reducing costs associated with transportation, accommodation, and training venues, thus lowering overall training costs and addressing the issues of long training cycles and high costs associated with traditional offline training. The learning map generation module dynamically generates personalized learning maps based on the job competency model and individual employee skills, providing targeted training tutorials and avoiding a uniform training model. Furthermore, the error correction reinforcement module provides reinforcement tutorials and tests targeting employees' weak areas, helping them accurately address their weaknesses, improve learning effectiveness, and quickly master the relevant knowledge and operational skills of new equipment and processes. This shortens job adaptability time and addresses the problem of slow adaptation to new environments. The assessment and points module allows for real-time evaluation of employee learning outcomes. The qualification linkage module links learning points to job qualification certification. Only employees whose points reach a preset threshold can obtain job qualification certification, ensuring that employees possess the necessary skills before starting work. This effectively reduces the risk of employee misoperation, guarantees the safety and stability of production in the new factory, and solves the problems of disconnect between traditional training effectiveness and job qualification, as well as the high risk of misoperation.

[0053] In fact, the list of job positions to be trained can also be generated by a deep learning model. For example, taking the equipment list and process improvement details of the old and new plants as input, a trained deep learning model can analyze the differences in equipment and processes between the old and new plants, and infer the list of job positions to be trained based on the output of these differences. It should be noted that training deep learning models is a conventional technique and will not be detailed here.

[0054] In addition, the existing expert database can be used to review the list of training positions. In this case, the expert database ensures the professionalism and rationality of the training position list, providing a foundation for subsequent personalized learning map generation and tutorial matching.

[0055] The following is a detailed explanation of each module of the online job adaptability training platform:

[0056] In the content generation module 110, the job training tutorials include various formats, such as videos, animations, simulated operations, and interactive quizzes. Compared with traditional offline lecture-based training, these tutorials are more interesting and interactive. At the same time, through incentive methods such as points accumulation and electronic qualification badges, employees are encouraged to learn actively, complete quizzes and correct mistakes, thereby improving their learning enthusiasm and initiative and further enhancing the quality of training.

[0057] The training job catalog in this embodiment is formulated by experts from the expert database based on the key equipment and new processes introduced in the new plant. During the commissioning and operation of the new plant, the training tutorials, question banks, and job qualification certification thresholds can be updated synchronously according to the iterative upgrades of equipment and processes. At the same time, the online platform can be connected to the company's existing OA system, IM platform, and job management system, adapting to the company's existing management model. It has good scalability and practicality and can serve the new plant's job training work for a long time.

[0058] The content generation module 110 in this embodiment includes a database, in which job training tutorials and an expert database can be set and stored.

[0059] In the learning map generation module 120, the job competency model of the target position can be quantitatively built based on the job competency of the original factory employees through the following indicators: job competency, long-term career competency, personal intrinsic qualities, and career evaluation cognition. These are called the four criteria for job competency. Based on the above four dimensional indicators, the initial job competency table (or job competency criteria) of the new factory position is constructed.

[0060] After obtaining the initial job competency table, it is necessary to continuously select the most relevant indicators from numerous job competency indicator terms as child nodes under each competency criterion. The competency criterion term nodes are then linked to the indicator term nodes, and this process is iterated until a complete job competency criterion tree is generated, resulting in a comprehensive job competency table. Whether or not a link is established between competency criterion terms and indicator terms is determined based on the similarity score between the two terms. If the semantic similarity between the two terms is high, they are considered sufficiently related and can be linked; otherwise, the correlation between the indicator term and the competency criterion is insufficient, and a link should not be established.

[0061] Similarity calculation methods are divided into dense semantic similarity calculation and sparse semantic similarity calculation. Dense semantic similarity calculation methods are stronger in terms of understanding and context relevance, but have poor interpretability. Sparse semantic similarity calculation methods are simple, fast, and handle low-frequency words well and have strong interpretability, but their semantic understanding is weak.

[0062] The dense semantic similarity score is calculated based on the similarity measure of word vectors or sentence vectors. The text vectors (A and B) of two words are calculated using a pre-trained WWM model. The dense semantic similarity score, denoted as Sd, is obtained by calculating the similarity between the two vectors. The calculation formula is as follows:

[0063] (1);

[0064] The BM25 model can be used to calculate the sparse semantic similarity score; the relevance score between a word and the document is calculated by considering the frequency of a word in the document and the length of the document.

[0065] The sparse semantic similarity score is denoted as Ss; the calculation formula is as follows:

[0066] (2);

[0067] In the formula, Words Frequency of occurrence in text D; Represents the text length; k and b are constants; Represents inverse document frequency, reflecting the rarity of a word in the entire corpus. Its calculation formula is shown below:

[0068] (3);

[0069] In the formula, Indicates included words The number of texts, where N represents the number of texts.

[0070] The dense semantic score and the sparse semantic score are obtained, and the two scores are combined to calculate the overall similarity score. The overall similarity score is S. Z The calculation formula is as follows:

[0071] (4);

[0072] In the formula, and Here, is a hyperparameter used to adjust the proportion of dense semantic score and sparse semantic score in the final total score, and the two hyperparameters satisfy:

[0073] (5).

[0074] In tutorial matching module 130, an authentication interface and an employee access interface are preset. The authentication interface uses "account password + enterprise employee ID dual verification" to ensure the security of employee access. The employee access interface connects with the OA system and IM platform (such as WeChat Work, DingTalk or Lark) using the HTTP / HTTPS protocol, and the data transmission format is JSON.

[0075] In the assessment points module 140, the preset points rules can be set as basic points + bonus points. Basic points: 1 point for answering a basic question correctly, 2 points for answering an advanced question correctly, and 3 points for answering a difficult question correctly. 0.5 points are deducted for any wrong answer. No points are awarded for not completing the test on time. Bonus points: 5 points are awarded for completing the learning node test for 7 consecutive days. 1 point is awarded for each corrected wrong answer. Points are valid for 6 months. Points that have not reached the qualification threshold by the expiration date will be cleared and the student will need to retake the test.

[0076] The job qualification certification thresholds are set according to the difficulty level of the job: 80 points for basic operation positions, 100 points for intermediate technical positions, and 120 points for senior management positions. The thresholds are jointly determined by experts from the expert database in conjunction with the job competency model.

[0077] In addition, the electronic qualification badge uses an encrypted QR code that contains information such as employee name, position, certification time, and validity period. It can be queried and verified through the enterprise's OA system and IM platform. The position access status update interface is connected to the enterprise's existing position management system (e.g., OA system). After the qualification linkage module outputs a trigger signal, it automatically updates the employee's access status from "pending certification" to "certified" and pushes the certification notification to the employee and the position management department at the same time.

[0078] In fact, the tutorial matching module connects to the identity verification interface to verify the legitimacy of the received employee identity information. Once the verification is successful, the employee is granted learning access permissions corresponding to their position.

[0079] In one implementation scenario, such as Figure 2 As shown, the learning map generation module 120 includes: a job tagging unit 121, which is used to establish a multi-dimensional tagging system for each target job, including equipment type, process flow, and operation difficulty level, so as to construct a job competency model for the target job;

[0080] The tutorial semantic association unit 122 is used to perform semantic analysis on the job training tutorial, generate tutorial tags, and add the tutorial tags to the multi-dimensional tag system.

[0081] The path planning engine 123 is used to preset learning path rules and generate personalized learning maps based on the multi-dimensional tag system, tutorial tags, and preset learning path rules.

[0082] In this embodiment, the job labeling unit 121 first collects information on the equipment type, process flow, and operation difficulty level of the target job, and establishes a multi-dimensional label library; such as equipment type labels: coiling equipment, packaging equipment; operation difficulty labels: basic, intermediate, advanced.

[0083] The semantic association unit 122 of the tutorial uses the TF-IDF algorithm (Term Frequency - Inverse Document Frequency) to perform semantic analysis on the training tutorial, extract the core tags of the tutorial, match them with the job tag library, and establish a tag correspondence table;

[0084] The path planning engine 123 generates a personalized learning map for each employee based on the tag correspondence table and the preset learning path rules. After generation, employees can submit adjustment requests, which can be fine-tuned after review by experts in the expert database.

[0085] This involves semantic analysis of job training tutorials to generate tutorial tags. Specifically, the TF-IDF algorithm can be combined with keyword matching. First, the core keywords in the training tutorials, such as equipment models, operating steps, and process parameters, can be extracted using the TF-IDF algorithm and then accurately matched with job tags.

[0086] In practice, the path planning engine matches as follows: job difficulty tags take priority, and employee learning efficiency takes secondary consideration. The priority order is: operation difficulty level tag > equipment type tag > process flow tag. At the same time, it combines the employee's historical answer accuracy rate. If the accuracy rate is ≥80%, advanced content can be recommended. If the accuracy rate is <60%, basic content needs to be strengthened to generate a personalized learning path.

[0087] In one implementation scenario, the tutorial matching module 130 can perform tutorial matching and output. Specifically, when an employee logs into the online training platform through the enterprise OA system or WeChat Work, the tutorial matching module 130 receives the employee's identity information and performs dual verification based on the authorized employee access interface. After successful verification, it outputs a personalized learning map associated with the employee's job position for the employee to study.

[0088] In fact, after the personalized learning map is output and displayed, it can automatically jump to the tutorial interface for employees to learn.

[0089] In one implementation scenario, such as Figure 3 As shown, the assessment and scoring module 140 includes:

[0090] The learning assessment submodule 141 is used to extract online question-answering units from a preset knowledge base and embed the online question-answering units into the learning nodes of the personalized learning map;

[0091] The points submodule 142 is used to obtain the trainee's answer results and calculate and accumulate the trainee's learning points according to the preset points rules.

[0092] The question bank for the online quiz unit can be sourced from: expert databases, equipment manufacturers, or part or all of the industry standard question bank. The difficulty level of the questions corresponds to the difficulty of the job, with 60% being basic questions, 30% being advanced questions, and 10% being difficult questions. Each learning node contains 3-5 quiz units, and the time limit for answering questions is 15-20 minutes. Failure to complete the quiz within the time limit is considered a failure.

[0093] In one embodiment, the assessment and scoring module 140 further includes a wrong-answer reinforcement submodule 143.

[0094] The error correction reinforcement submodule is used to retrieve and re-push reinforcement tutorials and test questions associated with the error from the content generation module 110 when a trainee makes n consecutive errors in the online question-answering unit, so that the trainee can learn and test; where n is greater than 2.

[0095] In the error correction submodule 143, the criteria for judging consecutive errors are: three consecutive questions answered incorrectly or two consecutive questions answered incorrectly on the same knowledge point.

[0096] Search: By accurately matching the knowledge point tags of wrong questions with the tutorial tags, a targeted reinforcement tutorial is pushed, which lasts 10-15 minutes, along with 2-3 similar test questions. Only after the employee completes the reinforcement learning and answers the test questions correctly can the subsequent learning nodes be unlocked.

[0097] In fact, reinforcement training materials and test questions can be the original job training materials, or they can be pre-designed materials related to the target job training.

[0098] In this embodiment, the preset learning path rules include mandatory order rules and selective recommendation rules;

[0099] The mandatory sequence rule requires that the content of the next learning node can only be unlocked after the online answer result of the previous learning node meets the passing condition;

[0100] The selective recommendation rule recommends supplementary learning content based on the trainee's job category and historical learning efficiency.

[0101] Specifically, supplementary learning content is recommended based on the employee's job category; for example, equipment operation positions are recommended to have content related to equipment maintenance and troubleshooting, while process R&D positions are recommended to have content related to process optimization and the application of new technologies. Based on the employee's historical learning efficiency (learning time, answer accuracy), advanced learning content is recommended for employees with high learning efficiency, while basic reinforcement content is recommended for employees with low learning efficiency.

[0102] In fact, an automatic update reminder function has been added to the content generation module 110. When new equipment or new processes are put into use, the platform will automatically send update reminders to experts in the expert database. Experts are required to update the relevant tutorials within 15 working days. A tutorial update review mechanism has been established. Updated tutorials must be reviewed and approved by more than two experts before they can be launched online. The question bank of the online quiz unit can adopt a combination of automatic update and manual supplementation. The platform will automatically update the questions from the industry standard question bank and the question bank provided by the equipment manufacturer on a regular basis.

[0103] In this embodiment, the qualification linkage module 150 acquires employee point data from the assessment and scoring module 140 in real time.

[0104] The score is compared with the preset job qualification certification threshold, and a job qualification certification trigger signal is automatically generated when the score reaches or exceeds the threshold.

[0105] Electronic qualification badges are pushed to employees through the employee access interface, and the enterprise job management system interface is called to update the employee job access status.

[0106] Generate an authentication report and send it simultaneously to the company's job management department for filing.

[0107] In this embodiment, after outputting the job qualification certification trigger signal, the qualification linkage module is further used for:

[0108] Electronic qualification badges are issued to trainees and their job access status is updated through the employee access interface.

[0109] In one implementation scenario, a data statistics and analysis module is also included, which is used to collect data such as employee learning time, answer accuracy rate, accumulated points, and distribution of incorrect questions, and generate employee learning reports and training effectiveness analysis reports to provide decision-making basis for the enterprise's human resources department and job management department; at the same time, training tutorials and learning path rules can be optimized based on the analysis results to improve training quality.

[0110] In one implementation scenario, an access control module is added to manage the access permissions of different roles. For example, employees can only access the learning map and quiz unit for their own positions, administrators can view all employee learning data, manage tutorials and question banks, and experts can participate in the formulation of job directories, tutorial review and question bank compilation to ensure the security and orderliness of the system operation.

[0111] In one implementation scenario, an offline learning function module is added. This module takes into account that some employees may have inconvenient network access and supplements the offline learning function. Employees can download training tutorials and quiz units in advance, complete the learning and quiz offline, and automatically synchronize the learning data and quiz results after the network is restored, thereby improving the convenience of training.

[0112] In another embodiment, such as Figure 4 As shown, a method for improving training effectiveness includes the following steps S110-S150;

[0113] S110. Generate and store job training tutorials based on the job list to be trained; the job list to be trained is formulated by experts in the expert database based on the key equipment and new processes introduced in the new plant.

[0114] Among them, the experts in the expert database, based on the key equipment introduced by the new plant, such as the coiling and packaging equipment, as well as the new production processes, sorted out several core positions to be trained: basic operation positions (coiling and packaging equipment operators), intermediate technical positions (equipment maintenance positions, process inspection positions), and senior management positions (position supervisor positions, process management positions). This formed a list of positions to be trained, which was then reviewed and approved by all experts before being entered into the content generation module.

[0115] Job training tutorials can be generated based on big data computing and deep learning models; they can also be generated through manual operation platforms. The tutorials can be presented in multiple formats: video tutorials, animated demonstrations, simulated operations, text explanations, and interactive quizzes. Video tutorials can be recorded by technical experts from the equipment manufacturer, demonstrating equipment operation steps and precautions; animated demonstrations are used to showcase the production process flow, intuitively presenting the connections between each step; simulated operations are used for employee hands-on practice, simulating equipment operation scenarios and supporting repeated practice; text explanations supplement theoretical knowledge such as equipment principles and process standards; interactive quizzes are embedded in key parts of the tutorials to check learning effectiveness in real time. After the tutorials are generated, they are reviewed and approved by at least two experts before being stored in the database.

[0116] S120. Obtain the job competency model of the target position, retrieve the target training tutorial associated with the job competency model from the job training tutorial, and dynamically generate a personalized learning map for each trainee of the target position according to the target training tutorial and the preset learning path rules.

[0117] S130. Based on the authorized employee access interface, respond to the received employee identity information and output a personalized learning map associated with the employee's position.

[0118] S140. Embed an online quiz unit in the learning node of the personalized learning map to obtain the quiz results of the trainees, and calculate and accumulate the learning points of the trainees according to the preset scoring rules.

[0119] S150. Compare the learning points with a preset job qualification certification threshold. When the learning points reach or exceed the job qualification certification threshold, output a job qualification certification trigger signal.

[0120] In this embodiment, the step of dynamically generating a personalized learning map includes:

[0121] Establish a multi-dimensional tagging system for each target position, including equipment type, process flow, and level of operational difficulty, in order to construct a job competency model for the target position;

[0122] Specifically, the establishment of a multi-dimensional labeling system...

[0123] Basic Operator (Coil-Joining Equipment Operator): Equipment Type Label = Coil-Joining Equipment; Process Flow Label = Coil-Joining Process; Operation Difficulty Level Label = Basic;

[0124] Intermediate Technical Position (Equipment Maintenance Position): Equipment Type Label = Rolling and Joining Equipment, Packaging Equipment; Process Flow Label = Equipment Maintenance Process, Troubleshooting Process; Operation Difficulty Level Label = Intermediate;

[0125] Senior Management Position (Process Management Position): Equipment Type Label = All Key Equipment; Process Flow Label = Entire Production Process; Operation Difficulty Level Label = Advanced.

[0126] Semantic analysis is performed on the job training tutorials to generate tutorial tags; these tutorial tags are then added to a multi-dimensional tag system.

[0127] Semantic analysis: Using a combination of TF-IDF algorithm and keyword matching, semantic analysis is performed on job training tutorials to extract core keywords, such as coiling equipment model, operating steps, process parameters, and fault types, to generate tutorial tags. These tutorial tags are then linked to the job's multi-dimensional tag system to establish a tag correspondence table.

[0128] The system presets learning path rules and generates personalized learning maps based on the multi-dimensional tag system, tutorial tags, and preset learning path rules.

[0129] In fact, the path planning engine dynamically generates a personalized learning map for each employee based on the tag correspondence table, preset learning path rules, and the employee's basic ability assessment results (basic, good, excellent).

[0130] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the electronic device described above can be referred to the corresponding steps in the aforementioned method, and will not be elaborated further here.

[0131] Based on the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by hardware or by using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause an electronic device (such as a personal computer, server, or network device, etc.) to execute the methods described in the various implementation scenarios of this application.

[0132] In summary, this application provides an online training platform for job adaptability and a method for improving training effectiveness. The platform replaces traditional offline on-site guidance and remote learning methods, allowing employees to learn anytime, anywhere without spending significant time traveling to training locations, thus greatly shortening the training cycle. The learning map generation module dynamically generates personalized learning maps based on the job competency model and individual employee skills, providing targeted training tutorials and avoiding a one-size-fits-all approach. Simultaneously, the error correction reinforcement module provides reinforcement tutorials and tests targeting employees' weak areas, helping them accurately address their weaknesses, improve learning effectiveness, and quickly master the relevant knowledge and operational skills of new equipment and processes. This shortens job adaptability time and addresses the issue of slow adaptation to new environments. The assessment and scoring module verifies employee learning effectiveness in real time, and the qualification linkage module links learning points to job qualification certification. Only employees with points reaching a preset threshold can obtain job qualification certification, ensuring that employees possess the necessary skills before starting work, effectively reducing the risk of employee misoperation, ensuring the safety and stability of new factory production, and solving the problems of disconnect between traditional training effectiveness and job qualification, and high risk of misoperation.

[0133] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code, which includes one or more executable instructions for implementing a specified logical function. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0134] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A job adaptability online training platform, characterized in that, The online training platform for job adaptability includes: The content generation module is used to generate and store job training tutorials based on the job list to be trained; the job list to be trained is formulated by experts in the expert database based on the key equipment and new processes introduced in the new plant. The learning map generation module is used to obtain the job competency model of the target position, retrieve the target training tutorial associated with the job competency model from the job training tutorial, and dynamically generate a personalized learning map for each trainee of the target position according to the target training tutorial and the preset learning path rules. The tutorial matching module is used to output a personalized learning map associated with the employee's job position in response to the received employee identity information, based on the authorized employee access interface. The assessment and scoring module is used to embed online quiz units in the learning nodes of the personalized learning map, obtain the trainees' quiz results, and calculate and accumulate the trainees' learning points according to the preset scoring rules. The qualification linkage module is used to compare the learning points with a preset job qualification certification threshold. When the learning points reach or exceed the job qualification certification threshold, a job qualification certification trigger signal is output.

2. The online job adaptability training platform according to claim 1, characterized in that, The learning map generation module includes a job tagging unit, which is used to establish a multi-dimensional tagging system for each target job, including equipment type, process flow, and operation difficulty level, in order to construct a job competency model for the target job. The tutorial semantic association unit is used to perform semantic analysis on the job training tutorial, generate tutorial tags, and add the tutorial tags to the multi-dimensional tag system. The path planning engine is used to preset learning path rules and generate personalized learning maps based on the multi-dimensional tag system, tutorial tags, and preset learning path rules.

3. The online job adaptability training platform according to claim 1, characterized in that, The assessment scoring module includes: The learning assessment submodule is used to extract online quiz units from a preset knowledge base and embed the online quiz units into the learning nodes of the personalized learning map. The points submodule is used to obtain the trainee's answer results and calculate and accumulate the trainee's learning points according to the preset points rules.

4. The online job adaptability training platform according to claim 3, characterized in that, The assessment and scoring module also includes a sub-module for reinforcing incorrect answers. The error correction reinforcement submodule is used to retrieve and re-push reinforcement tutorials and test questions associated with the error from the content generation module when a trainee makes n consecutive errors in the online question-answering unit, so that the trainee can learn and test; where n is greater than 2.

5. The online job adaptability training platform according to claim 1, characterized in that, After the job qualification certification trigger signal is output, the qualification linkage module is also used for: Electronic qualification badges are issued to trainees and their job access status is updated through the employee access interface.

6. The online job adaptability training platform according to claim 1, characterized in that, The employee access interface is either the organizational structure interface of an enterprise office automation system or the application development interface of an instant messaging platform.

7. The online job adaptability training platform according to claim 1, characterized in that, The preset learning path rules include mandatory sequence rules and selective recommendation rules; The mandatory sequence rule requires that the content of the next learning node can only be unlocked after the online answer result of the previous learning node meets the passing condition; The selective recommendation rule recommends supplementary learning content based on the trainee's job category and historical learning efficiency.

8. A method for improving training effectiveness based on an online job adaptability training platform according to any one of claims 1 to 7, characterized in that, Includes the following steps: Training tutorials are generated and stored based on the list of positions to be trained; the list of positions to be trained is created by experts in the expert database based on the key equipment and new processes introduced in the new plant. Obtain the job competency model of the target position, retrieve the target training tutorial associated with the job competency model from the job training tutorial, and dynamically generate a personalized learning map for each trainee of the target position according to the target training tutorial and the preset learning path rules. Based on the authorized employee access interface, in response to the received employee identity information, a personalized learning map associated with the employee's position is output. An online quiz unit is embedded in the learning node of the personalized learning map to obtain the trainee's quiz results and calculate and accumulate the trainee's learning points according to the preset scoring rules. The learning points are compared with a preset job qualification certification threshold. When the learning points reach or exceed the job qualification certification threshold, a job qualification certification trigger signal is output.

9. The method for improving training effectiveness according to claim 8, characterized in that, The steps for dynamically generating personalized learning maps include: Establish a multi-dimensional tagging system for each target position, including equipment type, process flow, and level of operational difficulty, in order to construct a job competency model for the target position; Semantic analysis is performed on the job training tutorials to generate tutorial tags; these tutorial tags are then added to a multi-dimensional tag system. The system presets learning path rules and generates personalized learning maps based on the multi-dimensional tag system, tutorial tags, and preset learning path rules.

Images